whatmodel.sh / Reka Core (2024-05-01)
Reka Core (2024-05-01)
↗ share
+ contribute
Reka Core (2024-05-01) is a closed-weights language model from Reka AI, released May 2024. Licence: proprietary.
Catalogue identity notes
Comparison-only: retired or no longer listed API model, kept so its independent runs can be scored. Dated Reka API snapshot reka-core-20240501 (the first Reka Core release); distinct from the catalogued reka-core-20240904. Reka's current docs list only reka-flash and reka-edge, so no API is asserted.
$ how it compares
The LLMs ranked either side of Reka Core (2024-05-01), out of 828 with a score, then more from Reka AI.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 451 |  StarChat2 15B v0.1 | 48±1 | local | ||
| 452 |  Code Millenials 34B | 48±1 | local | ||
| 453 | Reka Core (2024-05-01) | 48±1 | comparison only | ||
| 454 |  Gemini 1.5 Flash-8B (001) | 48±2 | comparison only | ||
| 455 |  T5 Large | 48±9 | local | ||
| more from Reka AI | |||||
| 572 | Reka Flash 21B (2024-02-26) | 43±1 | comparison only | ||
$ what it's good at
coding▁▁▁▃▅▇█▇▅▄▃▁ #372 of 524 * · 21% of its score · 1 test
Beats GLM-4.7-Flash, Qwen3-VL 8B Instruct, Qwen3-VL 4B Instruct here, though they rank higher overall. Trails DeepSeek LLM 67B Chat, WizardLM 70B V1.0, Phi-4-mini 3.8B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| CRUXEval (ZeroEval, 800 problems) | 46.3% ✎ | ▁▂▆▃▆█▆▃▂·▁▁ beats 12/47 | 21% |
chat & writing▁▁▁▃▅▄▆█▇▇▇▃ #301 of 463 * · 7.3% of its score · 1 test
Beats Mistral Small 4 (119B-A6.5B), Ministral 3 14B Reasoning 2512, Qwen2.5 Coder 32B Instruct here, though they rank higher overall. Trails Flan-T5 XXL, Granite 4.0 H 1B, Granite 4.0 1B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Polyrating rating (bias-aware re-fit of Chatbot Arena votes, mid-2024) | 1212.0 ✎ | ▂▁▂▁▃▇█▆▇▄▂▂ beats 84/95 | 7.3% |
math▁▂▃▅▇▅▅█▄▁▁▁ #375 of 462 * · 19% of its score · 2 tests
Beats Athene-70B here, though they rank higher overall. Trails Gemma 7B (base), DeepSeek R1 Distill Qwen 1.5B, Tulu 2 DPO 13B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| GSM8K (ZeroEval, zero-shot) | 87.4% ✎ | ▁▄·▁▄█▅▅▅███ beats 19/43 | 10% |
| MATH Level 5 (ZeroEval, 721 problems) | 21.9% ✎ | ▁▁▁▆█▂▇▇▄··▂ beats 10/38 | 9.1% |
other tests3 not in a task · 52% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| MMLU-Redux (ZeroEval, 2,778 questions) | 76.4% ✎ | ▁·▁▁▄▄▄▅█▄▂▁ beats 22/53 | 34% |
| ZebraLogic (ZeroEval, 1,000 puzzles) | 13.0% ✎ | ▁▁▃▆██▁▁·▁▁▁ beats 18/57 | 9.2% |
| WildBench v2 WB-Score (task macro) | 45.9028 WB-Score ✎ | ▁·▁▁·▃█▄▇▆▅▆ beats 36/52 | 8.2% |
$ where to run it
No verified API or download recorded yet · add one
$ how the score was worked out · WildEval ZeroEval published r… 84%, WildBench v2 leaderboard data… 8%, Polyrating: A Cost-Effective… 7%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 WildEval ZeroEval published results | 5 | 84% |
 WildBench v2 leaderboard data (Ai2) | 1 | 8% |
 Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3) | 1 | 7% |
| prior · pull toward the middle | 0% | |
| weighted average | = 48.2 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json